fidoptgreedy
greedy's deformable Quick Start command as first written (2019): NCC on a 2x2x2 window, 100x50x10 iterations, default smoothing; one intensity space, as its reference advises (NMI does not work very well for deformable registration).
RegistrationCPUversion picsl_greedy 1.4.0.3every datasetApache-2.0
Run it
With its KonfAI app, at the benchmark's settings (the fidopt app repositories are private for now: a Hugging Face token with access opens them):
pip install konfai-apps konfai-apps infer fideus-labs/fidopt-registration:Greedy -i fixed.nii.gz -i moving.nii.gz -o out
The app on Hugging Face: its model, its settings and how it is scored.
Where it works
Its place on each kind of problem it has results on, among the methods ranked there. A method that leads one problem can trail another: read the one closest to yours.
| Problem | Place | Ranked | Datasets |
|---|---|---|---|
| Repeat chest CT, same patient, tumour truth | 1 | of 5 | 1 of 1 |
| Simulated thoracic CBCT, known motion | 1 | of 4 | 1 of 1 |
| Repeat scans, same patient | 2 | of 5 | 1 of 1 |
| Rigid registration, CT to ultrasound | 2 | of 3 | 1 of 1 |
| Abdomen CT, same patient | not ranked yet | 1 of 3 | |
| Brain MR, inter-subject | not ranked yet | 1 of 4 | |
| Two modalities, same patient | not ranked yet | 2 of 5 | |
| Learn2Reg official validation pairs | not ranked yet | 1 of 4 | |
| Head, neck and spine, inter-patient | not ranked yet | 2 of 4 | |
| Abdomen MR, inter-patient | not ranked yet | 1 of 2 | |
| Radiographs (2D), inter-patient | not ranked yet | 1 of 2 | |
| Same patient, truth made by a program | not ranked yet | 2 of 8 |
Results
- Reference
- Yushkevich et al., Alzheimer's & Dementia 2016